{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 503, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.99, | |
"learning_rate": 7.582615760696608e-06, | |
"loss": 0.7539, | |
"step": 500 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 1006, | |
"num_train_epochs": 2, | |
"save_steps": 500, | |
"total_flos": 529879044096000.0, | |
"trial_name": null, | |
"trial_params": { | |
"learning_rate": 1.5075319081543059e-05, | |
"per_device_train_batch_size": 32 | |
} | |
} | |